Clearcrawl
Turn any public URL into clean markdown or JSON, and PDFs and spreadsheets into text
- Pricing
- Freemium
- Platforms
- API, Web, CLI
- Runs
- Remotely
- Version
- 0.4.2
- Listing updated
- 2 days ago
About Clearcrawl
Clearcrawl is a freemium MCP server for files and documents. It runs as a hosted remote server, so there is nothing to install locally.
Aimed at agents that need page text without ads, menus and footers, it returns title, author, date, text, links and tables for a public URL as markdown or JSON. A second tool converts PDF, XLSX, XLS, CSV and DOCX files into per-page text, sheet rows and records, or markdown tables. A PDF passed to the URL reader is billed as a conversion.
Calls are pay-per-use. 100 calls a day per IP need no key; beyond that credits are bought as prepaid packs through Stripe and the key is shown once after payment. Reads cost 2 credits and conversions 3 per page or sheet, at $0.001 a credit.
Limits are stated plainly: public http(s) URLs only, files up to 15 MB, no JavaScript rendering and no OCR yet. It runs on a free host, so the first call after idle can take about a minute. The MIT-licensed client can also read files from local disk in stdio mode.
Install
Run in a terminal
claude mcp add --transport http clearcrawl https://agentreader.onrender.com/clearcrawl/mcpAdd to Settings → Connectors → Add custom connector
https://agentreader.onrender.com/clearcrawl/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"clearcrawl": {
"url": "https://agentreader.onrender.com/clearcrawl/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"clearcrawl": {
"type": "http",
"url": "https://agentreader.onrender.com/clearcrawl/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"clearcrawl": {
"serverUrl": "https://agentreader.onrender.com/clearcrawl/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"clearcrawl": {
"type": "http",
"url": "https://agentreader.onrender.com/clearcrawl/mcp"
}
}
}Tools this server provides (2)
Taken from the project documentation; the running server may differ.
- read_url
- Reads a public URL into clean markdown or JSON.
- convert_file
- Converts a PDF, spreadsheet or DOCX into text and tables.
What it does
- URL to markdown or JSON
- Strips ads and navigation and returns text, links and tables.
- File conversion
- Converts PDF, XLSX, XLS, CSV and DOCX into text and tables.
- Free daily tier
- Gives 100 calls a day per IP with no key.
- Prepaid credits
- Sells packs from $5 for 5,000 credits.
- REST and MCP access
- Offers the same functions as REST endpoints and as a remote MCP server.
- Local file mode
- Converts files from disk when run through stdio.
Good for
- Feed an agent clean article text from a link
- Extract tables from a PDF report
- Turn a spreadsheet into records an agent can read
- Convert a DOCX into markdown
Pricing
Freemium
100 free calls/day; credit packs from $5 (read 2 credits, convert 3 per page)
Prices change. Check agentreader.onrender.com before you buy.
Clearcrawl FAQ
Is there a free tier?
Yes: 100 calls a day per IP with no signup.
How much do credits cost?
One credit is $0.001. Packs are $5 for 5,000, $20 for 22,000 and $50 for 60,000.
Can it read JavaScript-heavy pages or scanned PDFs?
Not yet. The docs say there is no JavaScript rendering or OCR.
What are the file limits?
Files up to 15 MB and public http(s) URLs only.
Is Clearcrawl free?
Clearcrawl has a free plan, with paid plans for more usage or features.
How do I add Clearcrawl to Claude Code?
Run this command in your terminal: claude mcp add --transport http clearcrawl https://agentreader.onrender.com/clearcrawl/mcp
What are the best alternatives to Clearcrawl?
The closest alternatives to Clearcrawl are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and ASTra.
Alternatives to Clearcrawl

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

ASTra
MCP serverLet agents read, edit, validate and undo Word .docx files with exact operations
Runs locally- 5 tools
- Freemium
- Files and documents

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools